Revelio

Tiny Papers at ICLR 2024

The black-box architecture of pretrained language models (PLMs) hinders the interpretability of lengthy responses in long-form question answering (LFQA). Prior studies use knowledge graphs (KGs) to enhance output transparency, but mostly focus on non-generative or short-form QA. We present Revelio, a new layer that maps PLM’s inner working onto a KG walk. Tests on two LFQA datasets show that Revelio supports PLM-generated answers with reasoning paths presented as rationales while retaining performance and time akin to their vanilla counterparts.

The code will be available soon!